What is Statistical Machine Translation?

Over the past few years, a transformation has taken place in machine translation tools as rule-based translation systems have given way to statistical language analysis techniques that use known translations (e.g., United Nations archives and other open content) to derive nuances and meanings not easily addressed by rule-based systems. Tools like Google Translate have used statistical methods to move machine translation to the point where it is now a viable, low-cost, and easy option for automated, rapid translation on web content. While the translation tools are not yet perfect, they are fairly accurate in most cases, and are well-suited for credible on-the-fly translations.

INSTRUCTIONS: Enter your responses to the questions below. This is most easily done by moving your cursor to the end of the last item and pressing RETURN to create a new bullet point. Please include URLs whenever you can (full URLs will automatically be turned into hyperlinks; please type them out rather than using the linking tools in the toolbar).

Please "sign" your contributions by marking with the code of 4 tildes (~) in a row so that we can follow up with you if we need additional information or leads to examples- this produces a signature when the page is updated, like this: - alan alan Aug 13, 2010

(1) How might this technology be relevant to the educational sector you know best?

  • It's hugely relevant to learning foreign languages and, like the calculator for mathematics, changes what students can perform easily (now translation of written text from and into the foreign language is quick and easy, on one level). Simultaneous interpretation is developing fast as well (speak into your iPhone and it speaks your message in the target language). A danger of this is that it may no longer seem worth the effort of learning a foreign language, getting to know other people's cultures, and understanding each other... - roger.blamire roger.blamire Feb 27, 2011
  • The use of statistical translation dependents on a reliable database. This can be fairly 'brute force' in nature in that the original text is compared with similar text in the database, and based on the context (eg. where the question is asked, cultural expectations etc), can return a fairly accurate result. As such, this approach can possibly be extended beyond translation, eg. in discourse analysis and marking of essays. - horncheah horncheah Feb 27, 2011
  • As Roger mentions, it's valuable for foreign language education but not necessarily the way you would expect. Live Mocha (http://www.livemocha.com) networks language learners with native-speaking partners. E.g. an English speaker learning french would be matched with a french speaker learning English. In addition to chat sessions, learners record exercises that are critiqued by native speakers. Of course, the critique is usually written in the language being learned. So what does an English speaker do with a critique of his French exercise also written in French? Use machine translation to interpret the critque!- brandt.redd brandt.redd Feb 27, 2011

(2) What themes are missing from the above description that you think are important?

  • your response here
  • another response here

(3) What do you see as the potential impact of this technology on teaching, learning, or creative expression?

  • your response here
  • another response here

(4) Do you have or know of a project working in this area?

Please share information about related projects in our Horizon K-12 Project form.